Kemal Yaylali
ae58e33fe2
Makes a real annotation runnable locally without the 25 GB VEP cache, which is what the demo needs and what a reviewer can reproduce in minutes. - params.vep_database (VEP_DATABASE=true) queries Ensembl's public database instead of a local cache. Slower per variant and fewer fields, so --everything is swapped for the flags the loader actually stores. Its cache placeholder is NO_CACHE, not NO_FILE: Nextflow rejects two staged inputs sharing a filename. - PIPELINE_DATABASE_URL is handed to the pipeline when set. The loader runs inside a container, where the API's own localhost URL would point at the container itself. - README: how to run the UI's annotate button locally against host Nextflow + Docker. Verified end to end on pipeline/tests/data/tiny.vcf: bcftools norm split the multiallelic record, VEP 113 annotated 4 variants live, the loader wrote them and marked the job succeeded, and the UI shows them. The deletion came back as 22:42126611 CT>C with exact VCF alleles, which is the case the audit's ID-tagging fix exists for. Tests: api 51, loader 16, stub run 3/3; ruff, mypy clean.
27 lines
1.1 KiB
Plaintext
27 lines
1.1 KiB
Plaintext
#!/usr/bin/env nextflow
|
|
nextflow.enable.dsl = 2
|
|
|
|
include { NORMALISE } from './modules/normalise'
|
|
include { VEP } from './modules/vep'
|
|
include { LOAD_DB } from './modules/load_db'
|
|
|
|
workflow {
|
|
if (!params.vcf) error "Provide --vcf"
|
|
if (workflow.profile.tokenize(',').contains('gcp') && !(params.project && params.bucket)) {
|
|
error "The gcp profile needs --project and --bucket (or GCP_PROJECT and GCS_BUCKET)"
|
|
}
|
|
// Stub runs (CI) have no VEP cache or plugin data on disk.
|
|
def must_exist = !workflow.stubRun
|
|
|
|
vcf_ch = Channel.fromPath(params.vcf, checkIfExists: true)
|
|
// In database mode there is no cache to stage. Its placeholder differs from the plugin one:
|
|
// Nextflow rejects two staged inputs that share a filename.
|
|
cache = file(params.vep_database ? "${projectDir}/assets/NO_CACHE" : params.vep_cache,
|
|
checkIfExists: must_exist && !params.vep_database)
|
|
plugins = file(params.vep_plugin_data ?: "${projectDir}/assets/NO_FILE", checkIfExists: must_exist)
|
|
|
|
NORMALISE(vcf_ch)
|
|
VEP(NORMALISE.out.vcf, cache, plugins)
|
|
LOAD_DB(VEP.out.tsv, params.job_id ?: 'dry-run')
|
|
}
|